Improving drone localisation around wind turbines using monocular model-based tracking

Oliver Moolan-Feroze; Konstantinos Karachalios; Dimitrios Nikolaidis; Andrew Calway

doi:10.1109/ICRA.2019.8794156

Improving drone localisation around wind turbines using monocular model-based tracking

Oliver Moolan-Feroze, Konstantinos Karachalios, Dimitrios Nikolaidis, Andrew Calway

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

10 Citations (Scopus)

190 Downloads (Pure)

Abstract

We present a novel method of integrating image-based measurements into a drone navigation system for the automated inspection of wind turbines. We take a model-based tracking approach, where a 3D skeleton representation of the turbine is matched to the image data. Matching is based on comparing the projection of the representation to that inferred from images using a convolutional neural network. This enables us to find image correspondences using a generic turbine model that can be applied to a wide range of turbine shapes and sizes. To estimate 3D pose of the drone, we fuse the network output with GPS and IMU measurements using a pose graph optimiser. Results illustrate that the use of the image measurements significantly improves the accuracy of the localisation over that obtained using GPS and IMU alone.

Original language	English
Title of host publication	2019 IEEE International Conference on Robotics and Automation (ICRA 2019)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	7713 - 7719
Number of pages	7
ISBN (Print)	9781538681763
DOIs	https://doi.org/10.1109/ICRA.2019.8794156
Publication status	E-pub ahead of print - 12 Aug 2019
Event	2019 IEEE International Conference on Robotics and Automation (ICRA 2019) - Montreal, Canada Duration: 20 May 2019 → 24 May 2019 https://www.icra2019.org/

Publication series

Name	l: IEEE International Conference on Robotics and Automation
Publisher	IEEE
ISSN (Print)	1050-4729
ISSN (Electronic)	2577-087X

Conference

Conference	2019 IEEE International Conference on Robotics and Automation (ICRA 2019)
Abbreviated title	ICRA2019
Country/Territory	Canada
City	Montreal
Period	20/05/19 → 24/05/19
Internet address	https://www.icra2019.org/

Access to Document

10.1109/ICRA.2019.8794156

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at https://ieeexplore.ieee.org/document/8794156. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 3.35 MB

Handle.net

Persistent link

Professor Andrew Calway
- Andrew.Calwaybristol.acuk
- School of Computer Science - Professor of Computer Vision
- Visual Information Laboratory
Person: Academic , Member

Cite this

Moolan-Feroze, O., Karachalios, K., Nikolaidis, D., & Calway, A. (2019). Improving drone localisation around wind turbines using monocular model-based tracking. In 2019 IEEE International Conference on Robotics and Automation (ICRA 2019) (pp. 7713 - 7719). (l: IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers (IEEE). Advance online publication. https://doi.org/10.1109/ICRA.2019.8794156

Moolan-Feroze, Oliver ; Karachalios, Konstantinos ; Nikolaidis, Dimitrios et al. / Improving drone localisation around wind turbines using monocular model-based tracking. 2019 IEEE International Conference on Robotics and Automation (ICRA 2019). Institute of Electrical and Electronics Engineers (IEEE), 2019. pp. 7713 - 7719 (l: IEEE International Conference on Robotics and Automation).

@inproceedings{d2e77692ab6d4f6fbc526a0ff66739cc,

title = "Improving drone localisation around wind turbines using monocular model-based tracking",

abstract = "We present a novel method of integrating image-based measurements into a drone navigation system for the automated inspection of wind turbines. We take a model-based tracking approach, where a 3D skeleton representation of the turbine is matched to the image data. Matching is based on comparing the projection of the representation to that inferred from images using a convolutional neural network. This enables us to find image correspondences using a generic turbine model that can be applied to a wide range of turbine shapes and sizes. To estimate 3D pose of the drone, we fuse the network output with GPS and IMU measurements using a pose graph optimiser. Results illustrate that the use of the image measurements significantly improves the accuracy of the localisation over that obtained using GPS and IMU alone.",

author = "Oliver Moolan-Feroze and Konstantinos Karachalios and Dimitrios Nikolaidis and Andrew Calway",

year = "2019",

month = aug,

day = "12",

doi = "10.1109/ICRA.2019.8794156",

language = "English",

isbn = "9781538681763",

series = "l: IEEE International Conference on Robotics and Automation",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "7713 -- 7719",

booktitle = "2019 IEEE International Conference on Robotics and Automation (ICRA 2019)",

address = "United States",

note = "2019 IEEE International Conference on Robotics and Automation (ICRA 2019), ICRA2019 ; Conference date: 20-05-2019 Through 24-05-2019",

url = "https://www.icra2019.org/",

}

Moolan-Feroze, O, Karachalios, K, Nikolaidis, D & Calway, A 2019, Improving drone localisation around wind turbines using monocular model-based tracking. in 2019 IEEE International Conference on Robotics and Automation (ICRA 2019). l: IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers (IEEE), pp. 7713 - 7719, 2019 IEEE International Conference on Robotics and Automation (ICRA 2019), Montreal, Quebec, Canada, 20/05/19. https://doi.org/10.1109/ICRA.2019.8794156

Improving drone localisation around wind turbines using monocular model-based tracking. / Moolan-Feroze, Oliver; Karachalios, Konstantinos; Nikolaidis, Dimitrios et al.
2019 IEEE International Conference on Robotics and Automation (ICRA 2019). Institute of Electrical and Electronics Engineers (IEEE), 2019. p. 7713 - 7719 (l: IEEE International Conference on Robotics and Automation).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Improving drone localisation around wind turbines using monocular model-based tracking

AU - Moolan-Feroze, Oliver

AU - Karachalios, Konstantinos

AU - Nikolaidis, Dimitrios

AU - Calway, Andrew

PY - 2019/8/12

Y1 - 2019/8/12

N2 - We present a novel method of integrating image-based measurements into a drone navigation system for the automated inspection of wind turbines. We take a model-based tracking approach, where a 3D skeleton representation of the turbine is matched to the image data. Matching is based on comparing the projection of the representation to that inferred from images using a convolutional neural network. This enables us to find image correspondences using a generic turbine model that can be applied to a wide range of turbine shapes and sizes. To estimate 3D pose of the drone, we fuse the network output with GPS and IMU measurements using a pose graph optimiser. Results illustrate that the use of the image measurements significantly improves the accuracy of the localisation over that obtained using GPS and IMU alone.

AB - We present a novel method of integrating image-based measurements into a drone navigation system for the automated inspection of wind turbines. We take a model-based tracking approach, where a 3D skeleton representation of the turbine is matched to the image data. Matching is based on comparing the projection of the representation to that inferred from images using a convolutional neural network. This enables us to find image correspondences using a generic turbine model that can be applied to a wide range of turbine shapes and sizes. To estimate 3D pose of the drone, we fuse the network output with GPS and IMU measurements using a pose graph optimiser. Results illustrate that the use of the image measurements significantly improves the accuracy of the localisation over that obtained using GPS and IMU alone.

U2 - 10.1109/ICRA.2019.8794156

DO - 10.1109/ICRA.2019.8794156

M3 - Conference Contribution (Conference Proceeding)

SN - 9781538681763

T3 - l: IEEE International Conference on Robotics and Automation

SP - 7713

EP - 7719

BT - 2019 IEEE International Conference on Robotics and Automation (ICRA 2019)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2019 IEEE International Conference on Robotics and Automation (ICRA 2019)

Y2 - 20 May 2019 through 24 May 2019

ER -

Moolan-Feroze O, Karachalios K, Nikolaidis D, Calway A. Improving drone localisation around wind turbines using monocular model-based tracking. In 2019 IEEE International Conference on Robotics and Automation (ICRA 2019). Institute of Electrical and Electronics Engineers (IEEE). 2019. p. 7713 - 7719. (l: IEEE International Conference on Robotics and Automation). Epub 2019 Aug 12. doi: 10.1109/ICRA.2019.8794156

Improving drone localisation around wind turbines using monocular model-based tracking

Abstract

Publication series

Conference

Access to Document

Handle.net

Fingerprint

Profiles

Professor Andrew Calway

Cite this